| CARVIEW |
Select Language
HTTP/2 200
server: GitHub.com
content-type: text/html; charset=utf-8
last-modified: Mon, 15 Dec 2025 00:29:09 GMT
access-control-allow-origin: *
strict-transport-security: max-age=31556952
etag: W/"693f5655-838e"
expires: Mon, 29 Dec 2025 17:25:24 GMT
cache-control: max-age=600
content-encoding: gzip
x-proxy-cache: MISS
x-github-request-id: 6732:318CF6:910B0C:A2CAC0:6952B72C
accept-ranges: bytes
age: 0
date: Mon, 29 Dec 2025 17:15:24 GMT
via: 1.1 varnish
x-served-by: cache-bom-vanm7210043-BOM
x-cache: MISS
x-cache-hits: 0
x-timer: S1767028525.547632,VS0,VE214
vary: Accept-Encoding
x-fastly-request-id: 00729013f93eb00f8ee7eef434ec595476800ce1
content-length: 6659
Zhenyu "Allen" Zhang
M.E. in University of Science and Technology of China
B.S. in University of Science and Technology of China
-
Hi there! I'm Zhenyu
I'm a final-year Ph.D. student at the Electrical and Computer Engineering Department of UT Austin, working with Prof. Atlas Wang. Previously, I had the opportunity to broaden my practical AI skills while collaborating with Prof. Beidi Chen at CMU and Dr. Yuandong Tian at Meta.
My research aims to develop Efficient, Scalable, and Steerable machine learning algorithms and systems, with specific interests in: (i) Model Reasoning (RL, Test-time Scaling, and Mechanistic Interpretability) (ii) Scalable Optimization for GenAI Model Training, (iii) Efficient Inference Algorithms, and (iv) Long-Context Modeling and Generation
I was recognized as an ML and Systems Rising Star in 2025 and received the MLSys'25 Outstanding Paper Award (Honorable Mention), along with several travel and reviewer awards from prestigious conferences.
Education
Ph.D. in The University of Texas at Austin
M.E. in University of Science and Technology of China
Sep 2019 - May 2022
M.E. in Electrical and Computer Engineering
Advised by Prof. Bin Li.
B.S. in University of Science and Technology of China
Sep 2015 - May 2019
B.S. in Applied Physics
Yan Ji-Ci Talent Program in Physics
Selected Publication
SEAL: Steerable Reasoning Calibration of Large Language Models for Free
Runjin Chen*, Zhenyu Zhang*, Junyuan Hong, Souvik Kundu, Zhangyang Wang (* Equal Contribution)
Conference on Language Modeling (COLM), 2025
APOLLO: SGD-like Memory, AdamW-level Performance
Hanqing Zhu*, Zhenyu Zhang*, Wenyan Cong, Xi Liu, Sem Park, Vikas Chandra, Bo Long, David Z. Pan, Zhangyang Wang, Jinwon Lee (* Equal Contribution)
Proceedings of Machine Learning and Systems (MLSys Outstanding Paper Award Honorable Mention), 2025
[Paper] [Project] [Code] [Hacker News] [LLaMA-Factory] [FluxML] [HuggingFace] [Axolotl] [Video] [机器之心]
R-Sparse: Rank-Aware Activation Sparsity for Efficient LLM Inference
Zhenyu Zhang, Zechun Liu, Yuandong Tian, Harshit Khaitan, Zhangyang Wang, Steven Li
International Conference on Learning Representations (ICLR), 2025
GaLore: Memory-Efficient LLM Training by Gradient Low-Rank Projection
Jiawei Zhao, Zhenyu Zhang, Beidi Chen, Zhangyang Wang, Anima Anandkumar, Yuandong Tian
International Conference on Machine Learning (ICML Oral), 2024
[Paper] [Project] [Code] [Hacker News] [HuggingFace] [LLaMA-Factory] [Axolotl] [AICoffeeBreak] [机器之心]
H2O: Heavy-Hitter Oracle for Efficient Generative Inference of Large Language Models
Zhenyu Zhang, Ying Sheng, Tianyi Zhou, Tianlong Chen, Lianmin Zheng, Ruisi Cai, Zhao Song, Yuandong Tian, Christopher Ré, Clark Barrett, Zhangyang Wang, Beidi Chen
Neural Information Processing Systems (NeurIPS), 2023
[Paper] [Project] [Code] [Meta/llama-recipes] [Answer.AI] [Talk] [新智元]
Work Experience
- Research on GenAI modeling for alpha prediction.
- Work with Dr. Wujie Huang.
- Research on mechanistic interpretability of reasoning models.
- Work with Dr. Shujian Zhang, Dr. John Lambert and Dr. Lun Wang.
- Research on efficient reasoning via activation engineering.
- Work with Dr. Shirley Wu, Dr. Qingyang Wu and Dr. Ben Athiwaratkun.
- Conducted research on building long context foundation models.
- Work with Dr. Souvik Kundu, Dr. Mostafa Hesham.
- Conduct research on efficient LLM inference by activation sparsity.
- Work with Dr. Steven Li, Dr. Zechun Liu, Dr. Yuandong Tian.
- Conduct research on enhancing context awareness of long-context LLMs.
- Work with Dr. Zhewei Yao, Dr. Xiaoxia Wu.
- Conduct research on KV cache compression for efficient LLM inference.
- Work with Dr. Bhavya Kailkhura, Dr. Brian Bartoldson, Dr. James Diffenderfer.